Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2052. Min Range: -5.2052
Max Act: 5.2052. Min Act: -0.1699
Data Index: 285439 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2052. Min Range: -5.2052
Max Act: 5.1115. Min Act: -0.1698
Data Index: 669428 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2052. Min Range: -5.2052
Max Act: 5.1115. Min Act: -0.1700
Data Index: 2081516 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2052. Min Range: -5.2052
Max Act: 5.0490. Min Act: -0.1700
Data Index: 4668688 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.9552. Min Act: -0.1700
Data Index: 285436 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.9240. Min Act: -0.1700
Data Index: 3689884 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.8927. Min Act: -0.1700
Data Index: 5720015 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.8927. Min Act: -0.1700
Data Index: 7401731 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.8302. Min Act: -0.1699
Data Index: 3055824 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7990. Min Act: -0.1700
Data Index: 669425 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7990. Min Act: -0.1700
Data Index: 4311404 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7990. Min Act: -0.1700
Data Index: 4973419 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7990. Min Act: -0.1699
Data Index: 5089568 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7677. Min Act: -0.1700
Data Index: 285440 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7365. Min Act: -0.1700
Data Index: 5634241 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7365. Min Act: -0.1700
Data Index: 6489415 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7052. Min Act: -0.1700
Data Index: 1989413 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7052. Min Act: -0.1700
Data Index: 705867 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.7052. Min Act: -0.1700
Data Index: 1806969 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2052. Min Range: -5.2052
Max Act: 4.6740. Min Act: -0.1699
Data Index: 4883179 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19